Multi-scale hierarchical recurrent neural networks for hyperspectral image classification
Shi, Cheng; Pun, Chi-Man
2018-03-13
Source PublicationNEUROCOMPUTING
ISSN0925-2312
Volume294Pages:82-93
Abstract

This paper presents a novel hyperspectral image (HSI) classification framework by exploiting multi-scale spectral-spatial features via hierarchical recurrent neural networks. The neighborhood information plays an important role in the image classification process. Convolutional neural networks (CNNs) have been shown to be effective in learning the local features of HSI. However, CNNs do not consider the spatial dependency of non-adjacent image patches. Recurrent neural networks (RNNs) can effectively establish the relationship of non-adjacent image patches, but it can only be applied to single-dimensional (1D) sequence. In this paper, we propose multi-scale hierarchical recurrent neural networks (MHRNNs) to learn the spatial dependency of non-adjacent image patches in the two-dimension (2D) spatial domain. First, to better represent the objects with different scales, we generate multi-scale 3D image patches of central pixel and surrounding pixels. Then, 3D CNNs extract the local spectral-spatial feature from each 3D image patch, respectively. Finally, multi-scale 1D sequences in eight directions are constructed on the 3D local feature domain, and MHRNNs are proposed to capture the spatial dependency of local spectralspatial features at different scales. The proposed method not only considers the local spectral-spatial features of the HSI, but also captures the spatial dependency of non-adjacent image patches at different scales. Experiments are performed on three real HSI datasets. The results demonstrate the superiority of the proposed method over several state-of-the-art methods in both visual appearance and classification accuracy. (C) 2018 Elsevier B.V. All rights reserved.

KeywordHyperspectral Image Classification Recurrent Neural Networks Multi-scale
DOI10.1016/j.neucom.2018.03.012
URLView the original
Indexed BySCIE
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000429324500009
PublisherELSEVIER SCIENCE BV
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:29   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorPun, Chi-Man
AffiliationDepartment of Computer and Information Science,University of Macau, Avenida da Universidade, Taipa, Macau,Macau S.A.R., China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Shi, Cheng,Pun, Chi-Man. Multi-scale hierarchical recurrent neural networks for hyperspectral image classification[J]. NEUROCOMPUTING,2018,294:82-93.
APA Shi, Cheng,&Pun, Chi-Man.(2018).Multi-scale hierarchical recurrent neural networks for hyperspectral image classification.NEUROCOMPUTING,294,82-93.
MLA Shi, Cheng,et al."Multi-scale hierarchical recurrent neural networks for hyperspectral image classification".NEUROCOMPUTING 294(2018):82-93.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shi, Cheng]'s Articles
[Pun, Chi-Man]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shi, Cheng]'s Articles
[Pun, Chi-Man]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shi, Cheng]'s Articles
[Pun, Chi-Man]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.